Hao Ren's scientific contributions

In the context of Industry 4.0, the paradigm of manufacturing has shifted from autonomous to intelligent by integrating advanced communication technologies. However, to enable manufacturers to respond quickly and accurately to the complex environment of manufacturing, knowledge of manufacturing required suitable representation. Ontology is a proper solution for knowledge representation, which is used to describe concepts and attributes in a specified domain. This paper proposes an ontology-based industrial model and significantly improves the interoperability of the models. Firstly, we conceptualize the attribute of the industrial models by providing concept and their properties in the schema layer of the ontology. Then, according to the data collected from the manufacturing system, several instances are created and stored in the data layer. In addition, we present a prototype distributed computing application. The result suggests that the ontology can optimize the management of industrial models and achieve interoperability between models.

This paper focuses on reviewing past progress in the advancement of definitions, methods, and models for safety analysis and assessment of process industrial systems and highlighting the main research topics. Based on the analysis of the knowledge with respect to process safety, the review covers the fact that the entire system does not have the ability to produce casualties, health deterioration, and other accidents, which ultimately cause human life threats and health damage. And, according to the comparison between safety and reliability, when a system is in an unreliable state, it must be in an unsafe state. Related works show that the main organizations and regulations are developed and grouped together, and these are also outlined in the literature. The progress and current research topics of the methods and models have been summarized and discussed in the analysis and assessment of safety for process industrial systems, which mainly illustrate that the dynamic operational safety assessment under the big data challenges will become the research direction, which will change the future study situation.

Modern industrial processes generate many inter-associated variables, which are more likely to implicit associations knowledge for describing irregular changes at different times to accurately describe behaviour changes. Motivated by this issue, a novel knowledge-data-based synchronization states analysis method is proposed for process monitoring. Its advantage mainly refers to integrating physical-chemical mechanism knowledge to handle the representation of associated relationships between numerous monitor variables. Furthermore, this method utilizes the trend distributions of variable changes to observe the differences between operation states and their parents online, which can maintain the simple, practical, and efficient advantage of data-driven process monitoring. Specifically, global process monitoring can be achieved by the synchronization status exceeding its corresponding threshold ( $\chi ^{2}$ distribution). At the same time, the local cause of backtracking can also be identified by whether the weighting of eigenvector components of each variable exceeds their corresponding thresholds ( $\chi ^{2}$ distribution). This novel proposed process monitoring method is applied to one practical hydrometallurgical zinc purification process consisting of copper and cobalt removal processes. The application's comparable performance shows the applicability and effectiveness of this proposed method.

Industrial process data reflects the dynamic changes of operation conditions, which mainly refer to the irregular changes in the dynamic associations between different variables in different time. And this related associations knowledge for process monitoring is often implicit in these dynamic monitoring data which always have richer operation condition information and have not been paid enough attention in current research. To this end, a new process monitoring method based on spatial-based graph convolution neural network (SGCN) is proposed to describe the characteristics of the dynamic associations which can be used to represent the operation status over time. Spatia-temporal graphs are firstly defined, which can be used to represent the characteristics of node attributes (dynamic edge features) dynamically changing with time. Then, the associations between monitoring variables at a certain time can be considered as the node attributes to define a snapshot of the static graph network at the certain time. Finally, the snapshot containing graph structure and node attributes is used as model inputs which are processed to implement graph classification by spatial-based convolution graph neural network with aggregate and readout steps. The feasibility and applicability of this proposed method are demonstrated by our experimental results of benchmark and practical case application.

The energy consumption prediction of chillers plays a central role in the optimization of the energy-saving control of central air-conditioning in a high-rise building. Existing deep neural network energy consumption prediction methods hardly combine operating data with empirical knowledge. Therefore, a new energy consumption prediction method based on graph sampling aggregation (GraphSAGE) network by using empirical knowledge to construct association graphs is proposed (EK-GraphSAGE). This method first uses the empirical knowledge that analyzes the operating status of chillers and combines the operating data of chillers to construct an association graph. Then the operating data and the association graph are input into the GraphSAGE network to predict the energy consumption of chillers. At last, an on-site experiment is carried out on the cold source system in a real building. The results show that the proposed method can achieve better prediction results compared with the state-of-the-art methods.

In order to satisfy safety requirements of plant-wide processes, distributed process monitoring methods are often used. However, few of them consider the problem on building multi-level knowledge blocks and the associations between different blocks, all of which are beneficial for plant-wide process monitoring in avoiding information conflict and even to improve monitoring accuracy. To handle these issues, a plant-wide process monitoring method is proposed, which is based on hierarchical graph representation learning with differentiable pooling by using multi-level knowledge graph (MLKG). Specifically, MLKG consists of devices level, subprocess level, process level, etc. Each level has numerous blocks (nodes) which is firstly constructed by priori-knowledge on monitoring variables to calculate the status of key components, such as the Hotelling's statistics. And then normalized mutual information (NMI) is used to obtain the associations between monitoring variables, and the status of each block on each level can be updated. Based on this method, MLKG can be completely constructed. In order to consider the association information of hierarchical representations of MLKG, the hierarchical graph representation learning is used to achieve plant-wide process monitoring. Results of case study on practical cobalt and nickel removal from zinc solution demonstrate the effectiveness and applicability of this method.

In order to satisfy safety requirements of modern plant-wide processes, multiblocks-based distributed monitoring strategies are often used to obtain higher monitoring performance, and their two critical issues refer to suitable multi-blocks partition for reducing uncertainties and local-global fault interpret perception for practical physical meaning. To handle these problems, a novel multi-level knowledge-graph (MLKG) based on combining domain experts knowledge and monitoring data are constructed to describe characteristics of plant-wide processes. And then numerous monitoring variables of each node (block) can be used to calculate the node status which can be used to realize fault detection by exceeding corresponding thresholds. Creatively, numerous node status of multi-level can be aggregated into the top-level node status to globally characterize the system health to realize fault detection. Finally, methods such as variables contribute rate can be adopted to locally locate the fault to achieve fault location, which can be regarded as an attempt to interpret the fault detection results. Results of benchmark and practical-case-application can be used to demonstrate the effectiveness and applicability of this proposed method.